Matches in SemOpenAlex for { <https://semopenalex.org/work/W2130325614> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2130325614 abstract "There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images remains a difficult problem. To address this problem, we present the convolutional deep belief network, a hierarchical generative model which scales to realistic image sizes. This model is translation-invariant and supports efficient bottom-up and top-down probabilistic inference. Key to our approach is probabilistic max-pooling, a novel technique which shrinks the representations of higher layers in a probabilistically sound way. Our experiments show that the algorithm learns useful high-level visual features, such as object parts, from unlabeled images of objects and natural scenes. We demonstrate excellent performance on several visual recognition tasks and show that our model can perform hierarchical (bottom-up and top-down) inference over full-sized images." @default.
- W2130325614 created "2016-06-24" @default.
- W2130325614 creator A5022202456 @default.
- W2130325614 creator A5023259221 @default.
- W2130325614 creator A5064419280 @default.
- W2130325614 creator A5067036768 @default.
- W2130325614 date "2009-06-14" @default.
- W2130325614 modified "2023-10-09" @default.
- W2130325614 title "Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations" @default.
- W2130325614 cites W2100495367 @default.
- W2130325614 cites W2105464770 @default.
- W2130325614 cites W2108138754 @default.
- W2130325614 cites W2116064496 @default.
- W2130325614 cites W2120432001 @default.
- W2130325614 cites W2122808326 @default.
- W2130325614 cites W2122922389 @default.
- W2130325614 cites W2125663122 @default.
- W2130325614 cites W2136922672 @default.
- W2130325614 cites W2137234026 @default.
- W2130325614 cites W2139427956 @default.
- W2130325614 cites W2145889472 @default.
- W2130325614 cites W2147800946 @default.
- W2130325614 cites W2159291644 @default.
- W2130325614 cites W2162915993 @default.
- W2130325614 cites W2165828254 @default.
- W2130325614 cites W2168002178 @default.
- W2130325614 doi "https://doi.org/10.1145/1553374.1553453" @default.
- W2130325614 hasPublicationYear "2009" @default.
- W2130325614 type Work @default.
- W2130325614 sameAs 2130325614 @default.
- W2130325614 citedByCount "1929" @default.
- W2130325614 countsByYear W21303256142012 @default.
- W2130325614 countsByYear W21303256142013 @default.
- W2130325614 countsByYear W21303256142014 @default.
- W2130325614 countsByYear W21303256142015 @default.
- W2130325614 countsByYear W21303256142016 @default.
- W2130325614 countsByYear W21303256142017 @default.
- W2130325614 countsByYear W21303256142018 @default.
- W2130325614 countsByYear W21303256142019 @default.
- W2130325614 countsByYear W21303256142020 @default.
- W2130325614 countsByYear W21303256142021 @default.
- W2130325614 countsByYear W21303256142022 @default.
- W2130325614 countsByYear W21303256142023 @default.
- W2130325614 crossrefType "proceedings-article" @default.
- W2130325614 hasAuthorship W2130325614A5022202456 @default.
- W2130325614 hasAuthorship W2130325614A5023259221 @default.
- W2130325614 hasAuthorship W2130325614A5064419280 @default.
- W2130325614 hasAuthorship W2130325614A5067036768 @default.
- W2130325614 hasConcept C108583219 @default.
- W2130325614 hasConcept C119857082 @default.
- W2130325614 hasConcept C154945302 @default.
- W2130325614 hasConcept C204321447 @default.
- W2130325614 hasConcept C41008148 @default.
- W2130325614 hasConcept C48044578 @default.
- W2130325614 hasConcept C77088390 @default.
- W2130325614 hasConcept C8038995 @default.
- W2130325614 hasConcept C81363708 @default.
- W2130325614 hasConceptScore W2130325614C108583219 @default.
- W2130325614 hasConceptScore W2130325614C119857082 @default.
- W2130325614 hasConceptScore W2130325614C154945302 @default.
- W2130325614 hasConceptScore W2130325614C204321447 @default.
- W2130325614 hasConceptScore W2130325614C41008148 @default.
- W2130325614 hasConceptScore W2130325614C48044578 @default.
- W2130325614 hasConceptScore W2130325614C77088390 @default.
- W2130325614 hasConceptScore W2130325614C8038995 @default.
- W2130325614 hasConceptScore W2130325614C81363708 @default.
- W2130325614 hasFunder F4320332180 @default.
- W2130325614 hasLocation W21303256141 @default.
- W2130325614 hasOpenAccess W2130325614 @default.
- W2130325614 hasPrimaryLocation W21303256141 @default.
- W2130325614 hasRelatedWork W2389214306 @default.
- W2130325614 hasRelatedWork W3029198973 @default.
- W2130325614 hasRelatedWork W3123344745 @default.
- W2130325614 hasRelatedWork W3133861977 @default.
- W2130325614 hasRelatedWork W3167935049 @default.
- W2130325614 hasRelatedWork W3193565141 @default.
- W2130325614 hasRelatedWork W4220926404 @default.
- W2130325614 hasRelatedWork W4226493464 @default.
- W2130325614 hasRelatedWork W4293226380 @default.
- W2130325614 hasRelatedWork W4312417841 @default.
- W2130325614 isParatext "false" @default.
- W2130325614 isRetracted "false" @default.
- W2130325614 magId "2130325614" @default.
- W2130325614 workType "article" @default.